I think you’re overestimating how significant those numbers say political compatibility is. The study said that 4% of marriages are between a Republican and a Democrat, which *sounds* low, but given that something like 30% of people are Republicans and 30% Democrats and 40% Independents, you would only expect 9% from pure mixing. There are 17% between Independents and non-Independents, but from random mixing you would only expect 24%.
Given those numbers of Republicans, Democrats and Independents, I'm pretty sure from pure mixing you would expect 18% (not 9%) of marriages to be between a Republican and a Democrat and 48% (not 24%) between an Independent and non-Independent.
Explanation: simplifying to heterosexual relationships and assuming both Republicans and Democrats are 50-50 male-female, you would expect 9% of marriages to be between a male Republican and a female Democrat, and 9% to be between a male Democrat and a female Republican, making 18% Republican-Democrat marriages in total.
Very much enjoying reading these! In Definition 3 (an a-measure), it might be worth making it more conspicuous that the measure should not have a negative part as I somehow only spotted that on the third or fourth reading.
Minor maths error:
Given those numbers of Republicans, Democrats and Independents, I'm pretty sure from pure mixing you would expect 18% (not 9%) of marriages to be between a Republican and a Democrat and 48% (not 24%) between an Independent and non-Independent.
Explanation: simplifying to heterosexual relationships and assuming both Republicans and Democrats are 50-50 male-female, you would expect 9% of marriages to be between a male Republican and a female Democrat, and 9% to be between a male Democrat and a female Republican, making 18% Republican-Democrat marriages in total.